Product traceability is essential in modern manufacturing to ensure quality standards and regulatory compliance. It also provides transparency that resonates with customers’ growing emphasis on sustainability. Traditional methods of traceability verification often involve manual inspections, which are time-consuming and prone to human error. This paper proposes an automated approach leveraging machine learning to detect anomalies and gaps in product traceability within discrete production lines. The production line is modeled as discrete sequences, with process parameter names for each station hashed and represented as states in Markov Chains. Through continuous analysis, the system updates the Markov Chain model, adapting to changing production scenarios without manual intervention. Anomalies are detected based on deviations in transition probabilities, allowing for the automatic identification of traceability anomalies and gaps. This not only ensures the integrity of the production process but also optimizes operational efficiency, significantly reducing the need for manual oversight. The proof-of-concept is demonstrated in a case study at the automotive electronic manufacturing plant of Robert Bosch Elektronik GmbH, showcasing the effectiveness and scalability of the automated approach in real-world manufacturing environments.